Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words starting with hyper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    弃
    0.73
     track
    0.71
     held
    0.67
     system
    0.64
     overhead
    0.63
     trick
    0.62
    itute
    0.61
     বিরত
    0.61
     تشکیل
    0.61
     hacer
    0.61
    POSITIVE LOGITS
    aze
    0.84
    linkColor
    0.69
    ze
    0.68
     मेवा
    0.68
    kal
    0.67
     Prefecture
    0.66
     সোসাই
    0.65
    थ
    0.65
    acidade
    0.64
     laaj
    0.64
    Act Density 0.064%

    No Known Activations